Building production-grade AI systems, autonomous agents and intelligent software.
I build AI systems at the intersection of Machine Learning, Large Language Models and Software Engineering.
My primary focus is designing autonomous AI agents capable of long-term memory, planning, retrieval, tool use, structured reasoning and reliable execution in production environments.
Currently working as a Data Scientist, I combine ML, NLP and systems engineering to build intelligent applications powered by LLMs, Retrieval-Augmented Generation and modern AI infrastructure.
Production-oriented autonomous AI agent built on top of the Ouroboros runtime.
Core capabilities
- π§ Long-term memory
- π€ Autonomous task execution
- π RAG & hybrid retrieval
- π Multi-model routing
- π Tool calling
- π Scheduling & background tasks
- π Observability & tracing
- π Controlled self-improvement
- Autonomous AI Agents
- AI System Design
- Large Language Models
- Retrieval-Augmented Generation
- Agent Memory & Planning
- Multi-Agent Systems
- Information Retrieval
- Mathematical Optimization
- AI Evaluation & Observability
- Production ML Infrastructure
- Mathematical Optimization
- Deep Learning
- Reinforcement Learning
- Agent Evaluation
- Retrieval Systems
- Reliable AI Systems
- Reliability over hype
- Production-first mindset
- Systems thinking
- Observability by design
- Continuous learning
I believe the next generation of AI products will be built not only by larger models, but by robust systems that combine reasoning, memory, planning and reliable software engineering.


